Is Huihui-gemma-3n-E4B-it-abliterated or Qwen3-8B smaller?

Huihui-gemma-3n-E4B-it-abliterated is smaller at Q4_K_M: 3.95 GiB against 4.68 GiB.

Which uses less memory at long context?

Huihui-gemma-3n-E4B-it-abliterated — its KV cache at 32K context is 9.1x smaller, because of how its attention layers cache.

Model comparison

Huihui-gemma-3n-E4B-it-abliterated vs Qwen3-8B

At Q4_K_M, Huihui-gemma-3n-E4B-it-abliterated is the smaller download — 4,237,064,192 bytes against 5,027,783,488. At long context the gap widens: Huihui-gemma-3n-E4B-it-abliterated's KV cache at 32K is 9.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Huihui-gemma-3n-E4B-it-abliterated	Qwen3-8B
Parameters	7.8B	8.2B
Architecture	gemma3n	qwen3
Layers	35	36
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	33	51
Smallest quantization	2.57 GiB	2.12 GiB
Q4_K_M	3.95 GiB	4.68 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Huihui-gemma-3n-E4B-it-abliterated	Qwen3-8B	Ratio
4,096	0.11 GiB	0.56 GiB	5.14×
8,192	0.16 GiB	1.13 GiB	6.86×
16,384	0.27 GiB	2.25 GiB	8.23×
32,768	0.49 GiB	4.50 GiB	9.14×
65,536	0.93 GiB	9.00 GiB	9.68×
131,072	1.80 GiB	18.00 GiB	9.97×